© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 22915
    Prev
    Next
    INDEX
    Explanations

    sequences of asterisks or symbols, indicating special formatting or emphasis in text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.90
    migrationBuilder
    -0.83
    󠁧
    -0.72
     /\.(
    -0.71
    offsetof
    -0.69
    AccessorTable
    -0.67
     endregion
    -0.66
     useAppContext
    -0.65
    Datuak
    -0.64
     Bever
    -0.63
    POSITIVE LOGITS
     مرئيه
    0.60
    +"'
    0.58
    tagHelperRunner
    0.57
    WireFormatLite
    0.56
    SharedDtor
    0.55
     STEM
    0.52
    WebElementEntity
    0.52
    JpaRepository
    0.50
    ）.
    0.50
    Homer
    0.49
    Activations Density 0.003%

    No Known Activations